metadata fxn's ready, still working on fxn for searching the corpus

.gitignore

@@ -0,0 +1 @@
+.DS_Store

DESCRIPTION

@@ -0,0 +1,22 @@
+Package: rhindwai
+Type: Package
+Title: Interface to Hindwai Publishing OAI-PMH methods
+Version: 0.0.1
+License: C00
+Date: 2012-06-27
+Authors@R: c(person("Scott", "Chamberlain", role = c("aut", "cre"),
+    email = "myrmecocystus@gmail.com"))
+Description: A programmatic interface to the
+    Web Service methods provided by Hindwai.
+URL: https://github.com/ropensci/rhindwai
+Collate:
+    'getrecord.r'
+    'identify.r'
+    'listidentifiers.r'
+    'listmetadataformats.r'
+    'listrecords.r'
+    'listsets.r'
+    'getcorpus.r'
+    'journals.r'
+    'subjects.r'
+    'unzipcorpus.r'

NAMESPACE

@@ -0,0 +1,12 @@
+export(getcorpus)
+export(getrecord)
+export(identify)
+export(journals)
+export(listidentifiers)
+export(listmetadataformats)
+export(listrecords)
+export(listsets)
+export(subjects)
+export(unzipcorpus)
+import(OAIHarvester)
+import(XML)

R/.gitignore

@@ -0,0 +1 @@
+.DS_Store

R/getcorpus.r

@@ -0,0 +1,13 @@
+#' Download Hindawi corpus zip file to "~/".
+#' 
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' getcorpus()
+#' }
+#' @export
+getcorpus <- function()
+{
+  download.file(
+    url = "ftp://hindawi.corpus:download@ftp.hindawi.com/articles.zip", 
+    destfile = "~/hindwai_corpus.zip", quiet = TRUE)
+}

R/getrecord.r

@@ -0,0 +1,22 @@
+#' Retrieve an individual metadata record from a Hindawi Publishing Corporation repository.
+#'
+#' @import OAIHarvester
+#' @inheritParams listmetadataformats
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' out <- getrecord("10.1155/2011/391971", T)
+#' out$datestamp # get $identifier, $datestamp, $setSpec, or $metadata
+#' oaih_transform(out$metadata) # transform only metadata to a list
+#' }
+#' @export
+getrecord <- function(id = NULL, transform = TRUE, 
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx") 
+{
+  if(!is.null(id) == T) {oaiid <- paste("oai:hindawi.com:", id, sep="")} else
+      {oaiid <- NULL}
+	oaih_get_record(
+	  url, 
+		oaiid, 
+		prefix = "oai_dc", 
+		transform = transform)
+}

R/hindawi_search.r

@@ -0,0 +1,20 @@
+# #' Search the Hindawi corpus locally.
+# #' 
+# #' The Hindawi corpus zip file (http://www.hindawi.com/corpus/) is updated 
+# #'    every day. 
+# #'    
+# #' @import tm
+# #' @param terms Search terms.
+# #' @param fuzzy Fuzzy seearch? Defaults to FALSE.
+# #' @param journal_title Journal title to search.
+# #' @param year Year to search.
+# #' @param directory Defaults to where they were written with getcorpus().
+# #' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+# #' @examples \dontrun{
+# #' hindawi_search()
+# #' }
+# #' @export
+# hindawi_search <- function(terms = NA, , directory)
+# {
+# #   xmlParse("~/hindwai/2011/ISRN.SP/101582-2011-06-08.xml")
+# }

R/identify.r

@@ -0,0 +1,15 @@
+#' Retrieve information about the Hindwai repository.
+#'
+#' Learn about the Hindwai OAI-PMH service
+#' @import OAIHarvester
+#' @inheritParams listmetadataformats
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' identify()
+#' }
+#' @export
+identify <- function(transform = TRUE, 
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx") 
+{ 
+  oaih_identify(url, transform = transform)
+}

R/journals.r

@@ -0,0 +1,19 @@
+#' Get information on each journal.
+#'    
+#' @import XML
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' journals()
+#' }
+#' @export
+journals <- function()
+{
+  temp <- xmlParse("~/hindwai/Subjects.xml")
+  jtitle <- xpathSApply(temp, "//full.title", xmlValue)
+  issn <- xpathSApply(temp, "//e-issn", xmlValue)
+  doi <- xpathSApply(temp, "//doi", xmlValue)
+  startyear <- xpathSApply(temp, "//start.year", xmlValue)
+  pubyears <- xpathSApply(temp, "//publication.years", 
+                          function(x) c(xmlValue(x)))
+  data.frame(jtitle, issn, doi, startyear, pubyears)
+}

R/listidentifiers.r

@@ -0,0 +1,33 @@
+#' Retrieve an abbreviated form of List Records, retrieving only headers 
+#'    rather than records for specific volume in journal
+#'
+#' @import OAIHarvester
+#' @param from specifies that records returned must have been created/update/deleted 
+#'     on or after this date.
+#' @param until specifies that records returned must have been created/update/deleted 
+#'     on or before this date.
+#' @param set specifies the set that returned records must belong to.
+#' @param prefix specifies the metadata format that the records will be 
+#'     returned in. 
+#' @param token a token previously provided by the server to resume a request
+#'     where it last left off.
+#' @inheritParams listmetadataformats
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' temp <- listidentifiers()
+#' temp[[1]]
+#' listidentifiers(set = 'aaa:2007')
+#' }
+#' @export
+listidentifiers <- function(from = NULL, until = NULL, set = NULL, 
+  prefix = 'oai_dc', token = NULL, transform = TRUE,
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx")
+{
+  oaih_list_identifiers(
+    url, 
+    prefix = prefix,
+    from = from,
+    until = until,
+    set = set,
+    transform = transform)
+}

R/listmetadataformats.r

@@ -0,0 +1,15 @@
+#' Retrieve the metadata formats available from Hindawi Publishing Corporation repository.
+#'
+#' @import OAIHarvester
+#' @param transform transform metadata to list (TRUE/FALSE)
+#' @param url the base url for Hindwai (leave to default)
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' listmetadataformats()
+#' }
+#' @export
+listmetadataformats <- function(transform = TRUE,
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx") 
+{
+	oaih_list_metadata_formats(url, transform = transform)
+}

R/listrecords.r

@@ -0,0 +1,21 @@
+#' Harvest records from a Hindawi Publishing Corporation repository.
+#'
+#' @import OAIHarvester
+#' @inheritParams listidentifiers
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' listrecords(set = 'AMET:2012', transform=F)
+#' }
+#' @export
+listrecords <- function(from = NULL, until = NULL, set = NULL, prefix = 'oai_dc', 
+  token = NULL, transform = TRUE,
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx") 
+{
+	oaih_list_records(
+    url, 
+    prefix = prefix,
+    from = from,
+    until = until,
+    set = set,
+		transform = transform)
+}

R/listsets.r

@@ -0,0 +1,15 @@
+#' Retrieve the set structure of Hindawi Publishing Corporation repository.
+#'
+#' @import OAIHarvester
+#' @inheritParams listmetadataformats
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' sets <- listsets()
+#' head(sets)
+#' }
+#' @export
+listsets <- function(transform = TRUE,
+  url = "http://www.hindawi.com/oai-pmh/oai.aspx") 
+{ 
+	oaih_list_sets(url, transform = transform)
+}

R/subjects.r

@@ -0,0 +1,14 @@
+#' Get the subjects areas for Hindawi journals, and the journals that 
+#'    are in each subject.
+#'    
+#' @import XML
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' subjects()
+#' }
+#' @export
+subjects <- function()
+{
+  temp <- xmlParse("~/hindwai/Subjects.xml")
+  xpathSApply(temp, "//subject.title", xmlValue)
+}

R/unzipcorpus.r

@@ -0,0 +1,11 @@
+#' Unzip downloaded corpus after using getcorpus().
+#' 
+#' @author Scott Chamberlain \email{myrmecocystus@@gmail.com}
+#' @examples \dontrun{
+#' unzipcorpus()
+#' }
+#' @export
+unzipcorpus <- function()
+{
+  unzip("~/hindwai_corpus.zip", exdir="~/hindwai")
+}

README.md

@@ -1,4 +1,22 @@
 rhindawi
 ========
 
-R interface to the Hindawi Journals metadata and corpus
+Install using install_github within [Hadley's](https://github.com/hadley/devtools) devtools package.
+
+```R
+install.packages("devtools")
+require(devtools)
+install_github("rhindawi", "ropensci")
+require(rhindawi)
+```
+
+This package will access 1) Hindawi Journals metadata, and 2) the full corpus.  The full corpus is apparently updated daily. There is no API for the full text, but functions in this package (`getcorpus()`, `unzipcorpus()`, `hindawi_search()`) allow easy download and searching of the full corpus. 
+
+
++ [Hindawi Journals OAI-PMH metadata documentation](http://www.hindawi.com/oai-pmh/)
++ [Hindawi Journals corpus download](http://www.hindawi.com/corpus/)
++ [Documentation for OAI-PMH in general](http://www.openarchives.org/OAI/openarchivesprotocol.html)
+
+You do not need an API key, or other authentication.
+
+`rhindwai` is part of the rOpenSci project, visit http://ropensci.org to learn more.

man/getcorpus.Rd

@@ -0,0 +1,18 @@
+\name{getcorpus}
+\alias{getcorpus}
+\title{Download Hindawi corpus zip file to "~/".}
+\usage{
+  getcorpus()
+}
+\description{
+  Download Hindawi corpus zip file to "~/".
+}
+\examples{
+\dontrun{
+getcorpus()
+}
+}
+\author{
+  Scott Chamberlain \email{myrmecocystus@gmail.com}
+}
+

man/getrecord.Rd

@@ -0,0 +1,24 @@
+\name{getrecord}
+\alias{getrecord}
+\title{Retrieve an individual metadata record from a Hindawi Publishing Corporation repository.}
+\usage{
+  getrecord(id = NULL, transform = TRUE,
+    url = "http://www.hindawi.com/oai-pmh/oai.aspx")
+}
+\arguments{
+  \item{transform}{transform metadata to list (TRUE/FALSE)}
+
+  \item{url}{the base url for Hindwai (leave to default)}
+}
+\description{
+  Retrieve an individual metadata record from a Hindawi
+  Publishing Corporation repository.
+}
+\examples{
+\dontrun{
+out <- getrecord("10.1155/2011/391971", T)
+out$datestamp # get $identifier, $datestamp, $setSpec, or $metadata
+oaih_transform(out$metadata) # transform only metadata to a list
+}
+}
+

man/identify.Rd

@@ -0,0 +1,21 @@
+\name{identify}
+\alias{identify}
+\title{Retrieve information about the Hindwai repository.}
+\usage{
+  identify(transform = TRUE,
+    url = "http://www.hindawi.com/oai-pmh/oai.aspx")
+}
+\arguments{
+  \item{transform}{transform metadata to list (TRUE/FALSE)}
+
+  \item{url}{the base url for Hindwai (leave to default)}
+}
+\description{
+  Learn about the Hindwai OAI-PMH service
+}
+\examples{
+\dontrun{
+identify()
+}
+}
+

man/journals.Rd

@@ -0,0 +1,18 @@
+\name{journals}
+\alias{journals}
+\title{Get information on each journal.}
+\usage{
+  journals()
+}
+\description{
+  Get information on each journal.
+}
+\examples{
+\dontrun{
+journals()
+}
+}
+\author{
+  Scott Chamberlain \email{myrmecocystus@gmail.com}
+}
+